Paper Group ANR 1314
Learning Fair Classifiers in Online Stochastic Settings. DWnet: Deep-Wide Network for 3D Action Recognition. Exploring Multi-Banking Customer-to-Customer Relations in AML Context with Poincaré Embeddings. A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data. Device Scheduling with Fast Convergence for Wireless Feder …
Learning Fair Classifiers in Online Stochastic Settings
| Title | Learning Fair Classifiers in Online Stochastic Settings |
| Authors | Yi Sun, Ivan Ramirez, Alfredo Cuesta-Infante, Kalyan Veeramachaneni |
| Abstract | In many real life situations, including job and loan applications, gatekeepers must make justified, real time decisions about a person’s fitness for a particular opportunity using only a partial data set. People on both sides of such decisions have understandable concerns about their fairness, especially when they occur online or algorithmically. In this paper, we try to accomplish approximate group fairness in an online decision making process where examples are sampled i.i.d from an underlying distribution. The fairness metric we consider is equalized odds, which requires requires the decision making process to achieve approximately equalized false positive and false negative rates across demographic groups. Our work follows from the classical learning from experts scheme, extending theRandomized Multiplicative Weights algorithm by keeping separate weights for label classes as well as groups, where the probability of choosing each weights is optimized for both fairness and regret. Our theoretical results show that approximately equalized odds can be achieved without sacrificing much regret.We also demonstrate the performance of the algorithm on real data sets commonly used by the fairness community |
| Tasks | Decision Making |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.07009v2 |
| https://arxiv.org/pdf/1908.07009v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-fair-classifiers-in-online |
| Repo | |
| Framework | |
DWnet: Deep-Wide Network for 3D Action Recognition
| Title | DWnet: Deep-Wide Network for 3D Action Recognition |
| Authors | Yonghao Dang, Fuxing Yang, Jianqin Yin |
| Abstract | We propose in this paper a deep-wide network (DWnet) which combines the deep structure with the broad learning system (BLS) to recognize actions. Compared with the deep structure, the novel model saves lots of testing time and almost achieves real-time testing. Furthermore, the DWnet can capture better features than broad learning system can. In terms of methodology, we use pruned hierarchical co-occurrence network (PruHCN) to learn local and global spatial-temporal features. To obtain sufficient global information, BLS is used to expand features extracted by PruHCN. Experiments on two common skeletal datasets demonstrate the advantage of the proposed model on testing time and the effectiveness of the novel model to recognize the action. |
| Tasks | 3D Human Action Recognition |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11036v1 |
| https://arxiv.org/pdf/1908.11036v1.pdf | |
| PWC | https://paperswithcode.com/paper/dwnet-deep-wide-network-for-3d-action |
| Repo | |
| Framework | |
Exploring Multi-Banking Customer-to-Customer Relations in AML Context with Poincaré Embeddings
| Title | Exploring Multi-Banking Customer-to-Customer Relations in AML Context with Poincaré Embeddings |
| Authors | Lucia Larise Stavarache, Donatas Narbutis, Toyotaro Suzumura, Ray Harishankar, Augustas Žaltauskas |
| Abstract | In the recent years money laundering schemes have grown in complexity and speed of realization, affecting financial institutions and millions of customers globally. Strengthened privacy policies, along with in-country regulations, make it hard for banks to inner- and cross-share, and report suspicious activities for the AML (Anti-Money Laundering) measures. Existing topologies and models for AML analysis and information sharing are subject to major limitations, such as compliance with regulatory constraints, extended infrastructure to run high-computation algorithms, data quality and span, proving cumbersome and costly to execute, federate, and interpret. This paper proposes a new topology for exploring multi-banking customer social relations in AML context – customer-to-customer, customer-to-transaction, and transaction-to-transaction – using a 3D modeling topological algebra formulated through Poincar'e embeddings. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.07701v1 |
| https://arxiv.org/pdf/1912.07701v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-multi-banking-customer-to-customer |
| Repo | |
| Framework | |
A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data
| Title | A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data |
| Authors | Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A Velastin |
| Abstract | We present a new deep learning approach for real-time 3D human action recognition from skeletal data and apply it to develop a vision-based intelligent surveillance system. Given a skeleton sequence, we propose to encode skeleton poses and their motions into a single RGB image. An Adaptive Histogram Equalization (AHE) algorithm is then applied on the color images to enhance their local patterns and generate more discriminative features. For learning and classification tasks, we design Deep Neural Networks based on the Densely Connected Convolutional Architecture (DenseNet) to extract features from enhanced-color images and classify them into classes. Experimental results on two challenging datasets show that the proposed method reaches state-of-the-art accuracy, whilst requiring low computational time for training and inference. This paper also introduces CEMEST, a new RGB-D dataset depicting passenger behaviors in public transport. It consists of 203 untrimmed real-world surveillance videos of realistic normal and anomalous events. We achieve promising results on real conditions of this dataset with the support of data augmentation and transfer learning techniques. This enables the construction of real-world applications based on deep learning for enhancing monitoring and security in public transport. |
| Tasks | 3D Human Action Recognition, Data Augmentation, Temporal Action Localization, Transfer Learning |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.03520v1 |
| https://arxiv.org/pdf/1907.03520v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-for-real-time-3d |
| Repo | |
| Framework | |
Device Scheduling with Fast Convergence for Wireless Federated Learning
| Title | Device Scheduling with Fast Convergence for Wireless Federated Learning |
| Authors | Wenqi Shi, Sheng Zhou, Zhisheng Niu |
| Abstract | Owing to the increasing need for massive data analysis and model training at the network edge, as well as the rising concerns about the data privacy, a new distributed training framework called federated learning (FL) has emerged. In each iteration of FL (called round), the edge devices update local models based on their own data and contribute to the global training by uploading the model updates via wireless channels. Due to the limited spectrum resources, only a portion of the devices can be scheduled in each round. While most of the existing work on scheduling focuses on the convergence of FL w.r.t. rounds, the convergence performance under a total training time budget is not yet explored. In this paper, a joint bandwidth allocation and scheduling problem is formulated to capture the long-term convergence performance of FL, and is solved by being decoupled into two sub-problems. For the bandwidth allocation sub-problem, the derived optimal solution suggests to allocate more bandwidth to the devices with worse channel conditions or weaker computation capabilities. For the device scheduling sub-problem, by revealing the trade-off between the number of rounds required to attain a certain model accuracy and the latency per round, a greedy policy is inspired, that continuously selects the device that consumes the least time in model updating until achieving a good trade-off between the learning efficiency and latency per round. The experiments show that the proposed policy outperforms other state-of-the-art scheduling policies, with the best achievable model accuracy under training time budgets. |
| Tasks | |
| Published | 2019-11-03 |
| URL | https://arxiv.org/abs/1911.00856v1 |
| https://arxiv.org/pdf/1911.00856v1.pdf | |
| PWC | https://paperswithcode.com/paper/device-scheduling-with-fast-convergence-for |
| Repo | |
| Framework | |
Bundle Adjustment Revisited
| Title | Bundle Adjustment Revisited |
| Authors | Yu Chen, Yisong Chen, Guoping Wang |
| Abstract | 3D reconstruction has been developing all these two decades, from moderate to medium size and to large scale. It’s well known that bundle adjustment plays an important role in 3D reconstruction, mainly in Structure from Motion(SfM) and Simultaneously Localization and Mapping(SLAM). While bundle adjustment optimizes camera parameters and 3D points as a non-negligible final step, it suffers from memory and efficiency requirements in very large scale reconstruction. In this paper, we study the development of bundle adjustment elaborately in both conventional and distributed approaches. The detailed derivation and pseudo code are also given in this paper. |
| Tasks | 3D Reconstruction |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.03858v1 |
| https://arxiv.org/pdf/1912.03858v1.pdf | |
| PWC | https://paperswithcode.com/paper/bundle-adjustment-revisited |
| Repo | |
| Framework | |
Texture Fields: Learning Texture Representations in Function Space
| Title | Texture Fields: Learning Texture Representations in Function Space |
| Authors | Michael Oechsle, Lars Mescheder, Michael Niemeyer, Thilo Strauss, Andreas Geiger |
| Abstract | In recent years, substantial progress has been achieved in learning-based reconstruction of 3D objects. At the same time, generative models were proposed that can generate highly realistic images. However, despite this success in these closely related tasks, texture reconstruction of 3D objects has received little attention from the research community and state-of-the-art methods are either limited to comparably low resolution or constrained experimental setups. A major reason for these limitations is that common representations of texture are inefficient or hard to interface for modern deep learning techniques. In this paper, we propose Texture Fields, a novel texture representation which is based on regressing a continuous 3D function parameterized with a neural network. Our approach circumvents limiting factors like shape discretization and parameterization, as the proposed texture representation is independent of the shape representation of the 3D object. We show that Texture Fields are able to represent high frequency texture and naturally blend with modern deep learning techniques. Experimentally, we find that Texture Fields compare favorably to state-of-the-art methods for conditional texture reconstruction of 3D objects and enable learning of probabilistic generative models for texturing unseen 3D models. We believe that Texture Fields will become an important building block for the next generation of generative 3D models. |
| Tasks | |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07259v1 |
| https://arxiv.org/pdf/1905.07259v1.pdf | |
| PWC | https://paperswithcode.com/paper/texture-fields-learning-texture |
| Repo | |
| Framework | |
Meta Reinforcement Learning from observational data
| Title | Meta Reinforcement Learning from observational data |
| Authors | Quan Vuong, Shuang Liu, Minghua Liu, Kamil Ciosek, Hao Su, Henrik Iskov Christensen |
| Abstract | Pre-training is transformative in supervised learning: a large network trained with large and existing datasets can be used as an initialization when learning a new task. Such initialization speeds up convergence and leads to higher performance. In this paper, we seek to understand what the formalization for pre-training from only existing and observational data in Reinforcement Learning (RL) is and whether it is possible. We formulate the setting as Batch Meta Reinforcement Learning. We identify MDP mis-identification to be a central challenge and motivate it with theoretical analysis. Combining ideas from Batch RL and Meta RL, we propose tiMe, which learns distillation of multiple value functions and MDP embeddings from only existing data. In challenging control tasks and without additional exploration on unseen MDPs, tiMe is competitive with state-of-the-art model-free RL method trained with hundreds of thousands of interactions. This work demonstrates that Meta RL from observational data is possible and we hope it will gather additional interest from the community to tackle this problem. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11373v2 |
| https://arxiv.org/pdf/1909.11373v2.pdf | |
| PWC | https://paperswithcode.com/paper/pre-training-as-batch-meta-reinforcement |
| Repo | |
| Framework | |
On the Validity of Bayesian Neural Networks for Uncertainty Estimation
| Title | On the Validity of Bayesian Neural Networks for Uncertainty Estimation |
| Authors | John Mitros, Brian Mac Namee |
| Abstract | Deep neural networks (DNN) are versatile parametric models utilised successfully in a diverse number of tasks and domains. However, they have limitations—particularly from their lack of robustness and over-sensitivity to out of distribution samples. Bayesian Neural Networks, due to their formulation under the Bayesian framework, provide a principled approach to building neural networks that address these limitations. This paper describes a study that empirically evaluates and compares Bayesian Neural Networks to their equivalent point estimate Deep Neural Networks to quantify the predictive uncertainty induced by their parameters, as well as their performance in view of this uncertainty. In this study, we evaluated and compared three point estimate deep neural networks against comparable Bayesian neural network alternatives using two well-known benchmark image classification datasets (CIFAR-10 and SVHN). |
| Tasks | Image Classification |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01530v2 |
| https://arxiv.org/pdf/1912.01530v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-validity-of-bayesian-neural-networks |
| Repo | |
| Framework | |
Unforeseen Evidence
| Title | Unforeseen Evidence |
| Authors | Evan Piermont |
| Abstract | I propose a normative updating rule, extended Bayesianism, for the incorporation of probabilistic information arising from the process of becoming more aware. Extended Bayesianism generalizes standard Bayesian updating to allow the posterior to reside on richer probability space than the prior. I then provide an observable criterion on prior and posterior beliefs such that they were consistent with extended Bayesianism. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07019v2 |
| https://arxiv.org/pdf/1907.07019v2.pdf | |
| PWC | https://paperswithcode.com/paper/unforeseen-evidence |
| Repo | |
| Framework | |
Hyper-Molecules: on the Representation and Recovery of Dynamical Structures, with Application to Flexible Macro-Molecular Structures in Cryo-EM
| Title | Hyper-Molecules: on the Representation and Recovery of Dynamical Structures, with Application to Flexible Macro-Molecular Structures in Cryo-EM |
| Authors | Roy R. Lederman, Joakim andén, Amit Singer |
| Abstract | Cryo-electron microscopy (cryo-EM), the subject of the 2017 Nobel Prize in Chemistry, is a technology for determining the 3-D structure of macromolecules from many noisy 2-D projections of instances of these macromolecules, whose orientations and positions are unknown. The molecular structures are not rigid objects, but flexible objects involved in dynamical processes. The different conformations are exhibited by different instances of the macromolecule observed in a cryo-EM experiment, each of which is recorded as a particle image. The range of conformations and the conformation of each particle are not known a priori; one of the great promises of cryo-EM is to map this conformation space. Remarkable progress has been made in determining rigid structures from homogeneous samples of molecules in spite of the unknown orientation of each particle image and significant progress has been made in recovering a few distinct states from mixtures of rather distinct conformations, but more complex heterogeneous samples remain a major challenge. We introduce the ``hyper-molecule’’ framework for modeling structures across different states of heterogeneous molecules, including continuums of states. The key idea behind this framework is representing heterogeneous macromolecules as high-dimensional objects, with the additional dimensions representing the conformation space. This idea is then refined to model properties such as localized heterogeneity. In addition, we introduce an algorithmic framework for recovering such maps of heterogeneous objects from experimental data using a Bayesian formulation of the problem and Markov chain Monte Carlo (MCMC) algorithms to address the computational challenges in recovering these high dimensional hyper-molecules. We demonstrate these ideas in a prototype applied to synthetic data. | |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01589v1 |
| https://arxiv.org/pdf/1907.01589v1.pdf | |
| PWC | https://paperswithcode.com/paper/hyper-molecules-on-the-representation-and |
| Repo | |
| Framework | |
Answer Interaction in Non-factoid Question Answering Systems
| Title | Answer Interaction in Non-factoid Question Answering Systems |
| Authors | Chen Qu, Liu Yang, Bruce Croft, Falk Scholer, Yongfeng Zhang |
| Abstract | Information retrieval systems are evolving from document retrieval to answer retrieval. Web search logs provide large amounts of data about how people interact with ranked lists of documents, but very little is known about interaction with answer texts. In this paper, we use Amazon Mechanical Turk to investigate three answer presentation and interaction approaches in a non-factoid question answering setting. We find that people perceive and react to good and bad answers very differently, and can identify good answers relatively quickly. Our results provide the basis for further investigation of effective answer interaction and feedback methods. |
| Tasks | Information Retrieval, Question Answering |
| Published | 2019-01-11 |
| URL | http://arxiv.org/abs/1901.03491v2 |
| http://arxiv.org/pdf/1901.03491v2.pdf | |
| PWC | https://paperswithcode.com/paper/answer-interaction-in-non-factoid-question |
| Repo | |
| Framework | |
Trajectory growth lower bounds for random sparse deep ReLU networks
| Title | Trajectory growth lower bounds for random sparse deep ReLU networks |
| Authors | Ilan Price, Jared Tanner |
| Abstract | This paper considers the growth in the length of one-dimensional trajectories as they are passed through deep ReLU neural networks, which, among other things, is one measure of the expressivity of deep networks. We generalise existing results, providing an alternative, simpler method for lower bounding expected trajectory growth through random networks, for a more general class of weights distributions, including sparsely connected networks. We illustrate this approach by deriving bounds for sparse-Gaussian, sparse-uniform, and sparse-discrete-valued random nets. We prove that trajectory growth can remain exponential in depth with these new distributions, including their sparse variants, with the sparsity parameter appearing in the base of the exponent. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10651v1 |
| https://arxiv.org/pdf/1911.10651v1.pdf | |
| PWC | https://paperswithcode.com/paper/trajectory-growth-lower-bounds-for-random |
| Repo | |
| Framework | |
Spiking Networks for Improved Cognitive Abilities of Edge Computing Devices
| Title | Spiking Networks for Improved Cognitive Abilities of Edge Computing Devices |
| Authors | Anton Akusok, Kaj-Mikael Björk, Leonardo Espinosa Leal, Yoan Miche, Renjie Hu, Amaury Lendasse |
| Abstract | This concept paper highlights a recently opened opportunity for large scale analytical algorithms to be trained directly on edge devices. Such approach is a response to the arising need of processing data generated by natural person (a human being), also known as personal data. Spiking Neural networks are the core method behind it: suitable for a low latency energy-constrained hardware, enabling local training or re-training, while not taking advantage of scalability available in the Cloud. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09083v1 |
| https://arxiv.org/pdf/1912.09083v1.pdf | |
| PWC | https://paperswithcode.com/paper/spiking-networks-for-improved-cognitive |
| Repo | |
| Framework | |
A semi-supervised approach to message stance classification
| Title | A semi-supervised approach to message stance classification |
| Authors | Georgios Giasemidis, Nikolaos Kaplis, Ioannis Agrafiotis, Jason R. C. Nurse |
| Abstract | Social media communications are becoming increasingly prevalent; some useful, some false, whether unwittingly or maliciously. An increasing number of rumours daily flood the social networks. Determining their veracity in an autonomous way is a very active and challenging field of research, with a variety of methods proposed. However, most of the models rely on determining the constituent messages’ stance towards the rumour, a feature known as the “wisdom of the crowd”. Although several supervised machine-learning approaches have been proposed to tackle the message stance classification problem, these have numerous shortcomings. In this paper we argue that semi-supervised learning is more effective than supervised models and use two graph-based methods to demonstrate it. This is not only in terms of classification accuracy, but equally important, in terms of speed and scalability. We use the Label Propagation and Label Spreading algorithms and run experiments on a dataset of 72 rumours and hundreds of thousands messages collected from Twitter. We compare our results on two available datasets to the state-of-the-art to demonstrate our algorithms’ performance regarding accuracy, speed and scalability for real-time applications. |
| Tasks | Rumour Detection |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1902.03097v1 |
| http://arxiv.org/pdf/1902.03097v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-semi-supervised-approach-to-message-stance |
| Repo | |
| Framework | |
